{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RMJWPXIWT6RLY3WEJVPZBYJWRB","short_pith_number":"pith:RMJWPXIW","canonical_record":{"source":{"id":"2508.18421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T19:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"88030beb575582896c877ba70d8aaa4c1216f5014e4af9854947cb50b7d3b786","abstract_canon_sha256":"c6f1d698a757d5872c602106ac25ce0bdf421875b1b1de6ff693a8a8d0799a23"},"schema_version":"1.0"},"canonical_sha256":"8b1367dd169fa2bc6ec44d5f90e1368861ca681c1406b6b37aa081701d8b1cfc","source":{"kind":"arxiv","id":"2508.18421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18421","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18421v1","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18421","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"RMJWPXIWT6RL","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"RMJWPXIWT6RLY3WE","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"RMJWPXIW","created_at":"2026-07-05T11:59:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RMJWPXIWT6RLY3WEJVPZBYJWRB","target":"record","payload":{"canonical_record":{"source":{"id":"2508.18421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T19:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"88030beb575582896c877ba70d8aaa4c1216f5014e4af9854947cb50b7d3b786","abstract_canon_sha256":"c6f1d698a757d5872c602106ac25ce0bdf421875b1b1de6ff693a8a8d0799a23"},"schema_version":"1.0"},"canonical_sha256":"8b1367dd169fa2bc6ec44d5f90e1368861ca681c1406b6b37aa081701d8b1cfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:24.000936Z","signature_b64":"VkLQ4pubh7o0M6BBPjIhJzzsWUlfSv9QyFUV1cVXnlweBacC8PjJy9HOVaOSLccnGkUEJf8u+afeU0qD4kPTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1367dd169fa2bc6ec44d5f90e1368861ca681c1406b6b37aa081701d8b1cfc","last_reissued_at":"2026-07-05T11:59:24.000453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:24.000453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.18421","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSfngtO4SkGUmOnkU8JQiPM97PIl8oKwxjgncpoyz8Mr0fUuzMkPPaUXNo1c9ghKBRKqvgUUKWg4QFr+iNk9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:47:58.967652Z"},"content_sha256":"2bb7236cac668f26f0c3ea55663257a47bd830a83a7acbe9332e2994cee456fa","schema_version":"1.0","event_id":"sha256:2bb7236cac668f26f0c3ea55663257a47bd830a83a7acbe9332e2994cee456fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RMJWPXIWT6RLY3WEJVPZBYJWRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatemeh Ziaeetabar","submitted_at":"2025-08-25T19:11:03Z","abstract_excerpt":"Vision foundation models (FMs) have become the predominant architecture in computer vision, providing highly transferable representations learned from large-scale, multimodal corpora. Nonetheless, they exhibit persistent limitations on tasks that require explicit reasoning over entities, roles, and spatio-temporal relations. Such relational competence is indispensable for fine-grained human activity recognition, egocentric video understanding, and multimodal medical image analysis, where spatial, temporal, and semantic dependencies are decisive for performance. We advance the position that nex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18421","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.18421/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sUo/5/uVKlsrhlpBpPLZn+gxiFmKFKwJ+rRQkvrij5oTXqzZfMCNLhdMNJvQhTitgDbRXeF+Bg9fN3a2a/VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:47:58.968156Z"},"content_sha256":"50d696ba3bfa1f7d7848ac6b5ed3e173f5ca6775a2066d9796b7fd01cbc260e7","schema_version":"1.0","event_id":"sha256:50d696ba3bfa1f7d7848ac6b5ed3e173f5ca6775a2066d9796b7fd01cbc260e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/bundle.json","state_url":"https://pith.science/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T08:47:58Z","links":{"resolver":"https://pith.science/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB","bundle":"https://pith.science/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/bundle.json","state":"https://pith.science/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMJWPXIWT6RLY3WEJVPZBYJWRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RMJWPXIWT6RLY3WEJVPZBYJWRB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6f1d698a757d5872c602106ac25ce0bdf421875b1b1de6ff693a8a8d0799a23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T19:11:03Z","title_canon_sha256":"88030beb575582896c877ba70d8aaa4c1216f5014e4af9854947cb50b7d3b786"},"schema_version":"1.0","source":{"id":"2508.18421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18421","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18421v1","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18421","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"RMJWPXIWT6RL","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"RMJWPXIWT6RLY3WE","created_at":"2026-07-05T11:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"RMJWPXIW","created_at":"2026-07-05T11:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:50d696ba3bfa1f7d7848ac6b5ed3e173f5ca6775a2066d9796b7fd01cbc260e7","target":"graph","created_at":"2026-07-05T11:59:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.18421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision foundation models (FMs) have become the predominant architecture in computer vision, providing highly transferable representations learned from large-scale, multimodal corpora. Nonetheless, they exhibit persistent limitations on tasks that require explicit reasoning over entities, roles, and spatio-temporal relations. Such relational competence is indispensable for fine-grained human activity recognition, egocentric video understanding, and multimodal medical image analysis, where spatial, temporal, and semantic dependencies are decisive for performance. We advance the position that nex","authors_text":"Fatemeh Ziaeetabar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T19:11:03Z","title":"Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18421","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2bb7236cac668f26f0c3ea55663257a47bd830a83a7acbe9332e2994cee456fa","target":"record","created_at":"2026-07-05T11:59:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6f1d698a757d5872c602106ac25ce0bdf421875b1b1de6ff693a8a8d0799a23","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T19:11:03Z","title_canon_sha256":"88030beb575582896c877ba70d8aaa4c1216f5014e4af9854947cb50b7d3b786"},"schema_version":"1.0","source":{"id":"2508.18421","kind":"arxiv","version":1}},"canonical_sha256":"8b1367dd169fa2bc6ec44d5f90e1368861ca681c1406b6b37aa081701d8b1cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b1367dd169fa2bc6ec44d5f90e1368861ca681c1406b6b37aa081701d8b1cfc","first_computed_at":"2026-07-05T11:59:24.000453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:24.000453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VkLQ4pubh7o0M6BBPjIhJzzsWUlfSv9QyFUV1cVXnlweBacC8PjJy9HOVaOSLccnGkUEJf8u+afeU0qD4kPTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:24.000936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bb7236cac668f26f0c3ea55663257a47bd830a83a7acbe9332e2994cee456fa","sha256:50d696ba3bfa1f7d7848ac6b5ed3e173f5ca6775a2066d9796b7fd01cbc260e7"],"state_sha256":"cb4554aed7df8efb918b4e30aff42bd2100ee0883d4e60a85a0a2bdd7d7c6ff0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FwYdnSSquoPz1WmaTV9PXGdETqBHl9La8fjpDIbwg7AAXRymQctoViCmcP81Acpj+hddWz78yr8/hzfBXKfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:47:58.973201Z","bundle_sha256":"87690da6fa8778ee886515ca5ded1788a32a76417fbd3e7e418640be756ea6ab"}}